Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poisoning
    -0.08
    insula
    -0.08
    izzato
    -0.08
     immortal
    -0.07
     Planet
    -0.07
    enth
    -0.07
    نطق
    -0.07
     planet
    -0.07
    blick
    -0.07
     nier
    -0.07
    POSITIVE LOGITS
     Hatch
    0.08
    承德
    0.08
     Push
    0.08
    CAN
    0.08
    _MESSAGES
    0.07
     BSON
    0.07
     Ön
    0.07
    -blocking
    0.07
    ﺸ
    0.07
    后勤
    0.07
    Act Density 0.000%

    No Known Activations